Visual segmentation seeks to partition images, video frames, or point clouds into multiple
segments or groups. This technique has numerous real-world applications, such as …

Abstract 3D vision-language grounding (3D-VL) is an emerging field that aims to connect the
3D physical world with natural language, which is crucial for achieving embodied …

We address efficient and structure-aware 3D scene representation from images. Nerflets are
our key contribution--a set of local neural radiance fields that together represent a scene …

Abstract 3D vision-language (3D-VL) grounding, which aims to align language with 3D
physical environments, stands as a cornerstone in develo** embodied agents. In …

As the most fundamental scene understanding tasks, object detection and segmentation
have made tremendous progress in deep learning era. Due to the expensive manual …

Accurate and massive medical image annotation data is crucial for diagnosis, surgical
planning, and deep learning in the development of medical images. However, creating large …

Recently, transformer-based methods have dominated 3D instance segmentation, where
mask attention is commonly involved. Specifically, object queries are guided by the initial …

Human-centric scene understanding is significant for real-world applications, but it is
extremely challenging due to the existence of diverse human poses and actions, complex …